Remote GPU Infra SRE — Observability & Automation

Hamilton Barnes is seeking a Site Reliability Engineer to own the reliability of production GPU infrastructure and the associated observability stack. You will design dashboards, implement fast automation, and integrate ITSM tooling to automate workflows.

This is a fully remote role spanning the UK with a strong emphasis on low-latency performance and incident response. Ideal candidates have hands-on GPU infrastructure experience in production, deep Python skills for automation, and solid